© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117696
    Prev
    Next
    INDEX
    Explanations

    metal complex formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     econ
    -0.07
     सोसायटी
    -0.06
     deserts
    -0.06
     tü
    -0.06
     altering
    -0.06
    常用
    -0.06
     cercare
    -0.06
     adopting
    -0.06
    主に
    -0.06
     customary
    -0.06
    POSITIVE LOGITS
     cowboys
    0.06
     
    0.06
     firmly
    0.06
    Sorry
    0.05
     吸
    0.05
     axis
    0.05
     among
    0.05
     enggak
    0.05
     njima
    0.05
     નહીં
    0.05
    Activations Density 0.015%

    No Known Activations